# ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents

arXiv: https://arxiv.org/abs/2606.03239 · HTML: https://mlsanity.com/paper/2606.03239/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 31)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Prometheus: Inducing Fine-grained Evaluation Capability in Language Models](https://mlsanity.com/paper/2310.08491/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems](https://mlsanity.com/paper/2412.09413/) (2024)
- [DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research](https://mlsanity.com/paper/2511.19399/) (2025)
- [StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization](https://mlsanity.com/paper/2505.15107/) (2025)
- [Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning](https://mlsanity.com/paper/2508.16949/) (2025)
- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training](https://mlsanity.com/paper/2602.01511/) (2026)
- [s3: You Don't Need That Much Data to Train a Search Agent via RL](https://mlsanity.com/paper/2505.14146/) (2025)
- [Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling](https://mlsanity.com/paper/2510.17314/) (2025)
- [Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric](https://mlsanity.com/paper/2602.14069/) (2026)
- [TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs](https://mlsanity.com/paper/2603.22293/) (2026)
- [Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training](https://mlsanity.com/paper/2602.22576/) (2026)
- [AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning](https://mlsanity.com/paper/2603.21362/) (2026)
- [InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training](https://mlsanity.com/paper/2510.15859/) (2025)
- [LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization](https://mlsanity.com/paper/2505.17447/) (2025)
- [Hybrid Reward Normalization for Process-supervised Non-verifiable Agentic Tasks](https://mlsanity.com/paper/2509.25598/) (2025)

## Built on by (most cited first, 3 of 3)

- [SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning](https://mlsanity.com/paper/2607.26873/) (2026)
- [Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding Agents](https://mlsanity.com/paper/2609.31995/) (2026)
- [Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents](https://mlsanity.com/paper/2610.16998/) (2026)

## Abstract (arXiv)

LLM-based search agents are trained predominantly with outcome-only reward, leaving the search process itself unsupervised. This signal degenerates on outcome-homogeneous groups where all sampled trajectories share the same correctness, yielding zero within-group advantage and no gradient. Existing process supervision either trains a costly verifier or generates per-query rubrics that are inconsistent across queries and discarded after one use. We propose ARBOR (Adaptive Rubric Buffer for Online Reward), a reusable process-reward framework that maintains a rubric memory shared across queries. Query-local drafts induced from contrastive trajectories are admitted, consolidated into cross-query common rubrics, and retired as the policy evolves. A small active subset of common rubrics scores trajectories via sparse pairwise judging, and the resulting scores are added to the base reward, providing process-level gradient even when outcome reward is uniform. ARBOR consistently outperforms GRPO and DAPO baselines on four multi-hop QA benchmarks, raising average LLM-judge accuracy by up to 4.2 points and converting up to 42% of otherwise-zero-gradient training groups into informative ones.